IVF-TQ replaces learned codebooks with a fixed random rotation and precomputed scalar quantizer in the residual layer of an IVF index, delivering streaming recall stability at fixed bit budgets via a uniform-over-sphere inner-product bound.
hub
arXiv preprint arXiv:2502.02617
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
representative citing papers
Standard low-precision formats are suboptimal for vector direction preservation compared to optimized scalar alphabets and spherical codes, with gaps quantified analytically and proven in Lean, and NVIDIA's E2M1 nearly matching the optimum for 4 bits.
3DTurboQuant achieves training-free near-optimal quantization for 3DGS and DUSt3R models via random rotations inducing Beta distributions, enabling precomputed Lloyd-Max quantizers that deliver 3.5x and 7.9x compression with negligible quality loss.
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
OScaR mitigates token norm imbalance via canalized rotation and omni-token scaling to enable near-lossless INT2 KV cache quantization with up to 3x decoding speedup and 5.3x memory reduction.
Spherical KV combines angle-domain attention using spherical key codes with rate-distortion retention to cut KV cache residency and HBM traffic while keeping a paged, fusion-friendly decode path.
Fused compressed-domain int4 attention on Apple Silicon delivers 48x speedup and 3.2x KV cache compression for 128K-context 70B models while matching FP16 token predictions.
eOptShrinkQ compresses KV caches to ~2.2 bits per entry via optimal spectral shrinkage and quantization, outperforming prior methods on LongBench while matching FP16 on multi-needle retrieval.
AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.
TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a factor of approximately 2.7.
Hierarchical two-speed shared-weight recurrence in Transformers shows a sharp performance gap compared to independent layer stacking in empirical language modeling tests.
citing papers explorer
-
IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer
IVF-TQ replaces learned codebooks with a fixed random rotation and precomputed scalar quantizer in the residual layer of an IVF index, delivering streaming recall stability at fixed bit budgets via a uniform-over-sphere inner-product bound.
-
Direction-Preserving Number Representations
Standard low-precision formats are suboptimal for vector direction preservation compared to optimized scalar alphabets and spherical codes, with gaps quantified analytically and proven in Lean, and NVIDIA's E2M1 nearly matching the optimum for 4 bits.
-
3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models
3DTurboQuant achieves training-free near-optimal quantization for 3DGS and DUSt3R models via random rotations inducing Beta distributions, enabling precomputed Lloyd-Max quantizers that deliver 3.5x and 7.9x compression with negligible quality loss.
-
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
-
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
OScaR mitigates token norm imbalance via canalized rotation and omni-token scaling to enable near-lossless INT2 KV cache quantization with up to 3x decoding speedup and 5.3x memory reduction.
-
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
Spherical KV combines angle-domain attention using spherical key codes with rate-distortion retention to cut KV cache residency and HBM traffic while keeping a paged, fusion-friendly decode path.
-
Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon
Fused compressed-domain int4 attention on Apple Silicon delivers 48x speedup and 3.2x KV cache compression for 128K-context 70B models while matching FP16 token predictions.
-
eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization
eOptShrinkQ compresses KV caches to ~2.2 bits per entry via optimal spectral shrinkage and quantization, outperforming prior methods on LongBench while matching FP16 on multi-needle retrieval.
-
AXELRAM: Quantize Once, Never Dequantize
AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.
-
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a factor of approximately 2.7.
-
Hierarchical vs. Flat Iteration in Shared-Weight Transformers
Hierarchical two-speed shared-weight recurrence in Transformers shows a sharp performance gap compared to independent layer stacking in empirical language modeling tests.